We and selected third parties use cookies or similar technologies for technical purposes and, with your consent, to analyze how the site is used.

You can freely give, refuse or withdraw your consent at any time.

Google Kubernetes Engine (GKE), verified

MCP server by Google Cloud · Verified

Manage GKE clusters and node pools and inspect Kubernetes resources, events, logs and rollouts from your assistant.

OAuth sign-in (You sign in with the vendor the first time you connect)Streamable HTTP

Connect to Google Kubernetes Engine (GKE)

Google Kubernetes Engine (GKE) needs sign-in. Connect with its own URL:

https://container.googleapis.com/mcp

Your client opens Google Cloud’s sign-in the first time you use it. The token stays between your client and Google Cloud.

Share this server

Opens this page, with the URL and setup steps.

mcp.tc/i/gke

About

Connects to the Google Kubernetes Engine API and to the Kubernetes API of your clusters. You can list, create and update clusters and node pools, track GKE operations, and run kubectl-style actions such as get, describe, logs, events, rollout status and auth checks. It can also apply manifests, patch resources and delete resources.

Runs as a hosted streamable HTTP endpoint at https://container.googleapis.com/mcp. Access uses Google OAuth 2.0 and is governed by IAM permissions on your project and clusters. Several tools change or delete resources, so review calls before approving them.

What you can do

  • List, get, create and update GKE clusters
  • Create, list, inspect and update node pools
  • List, inspect and cancel GKE operations
  • Get and describe Kubernetes resources like kubectl
  • Read pod logs and cluster events
  • Check rollout status and permissions (auth can-i)
  • Apply manifests, patch and delete Kubernetes resources

Tools 27

  • list_k8s_api_resourcesRead-only

    List API groups and resources in a cluster, like kubectl api-resources.

  • check_k8s_authRead-only

    Check whether an action is allowed on a resource, like kubectl auth can-i.

  • describe_k8s_resourceRead-only

    Show details of a Kubernetes resource, like kubectl describe.

  • list_k8s_eventsRead-only

    Retrieve events from a Kubernetes cluster.

  • get_k8s_resourceRead-only

    Get resources filtered by type, name, namespace or labels, returned as YAML.

  • get_k8s_cluster_infoRead-only

    Get cluster endpoint information.

  • get_k8s_versionRead-only

    Get Kubernetes client and server versions for a cluster.

  • get_k8s_rollout_statusRead-only

    Check the rollout status of a Kubernetes resource.

  • list_clustersRead-only

    List GKE clusters in a project and location.

  • create_clusterWrites

    Create a GKE cluster, Autopilot by default.

  • update_clusterCan delete

    Update a specific GKE cluster.

  • get_clusterRead-only

    Get details of a specific GKE cluster.

Show 15 more tools
  • list_operationsRead-only

    List GKE operations in a project and location.

  • get_operationRead-only

    Get details of a specific GKE operation.

  • cancel_operationCan delete

    Cancel a specific GKE operation.

  • create_node_poolWrites

    Create a node pool in a GKE cluster.

  • list_node_poolsRead-only

    List node pools of a GKE cluster.

  • get_node_poolRead-only

    Get details of a node pool.

  • update_node_poolCan delete

    Update a node pool within a GKE cluster.

  • get_k8s_logsRead-only

    Get logs from a container in a pod, like kubectl logs.

  • apply_k8s_manifestCan delete

    Apply a manifest using server-side apply, with optional dry run.

  • delete_k8s_resourceCan delete

    Delete a Kubernetes resource, with optional dry run.

  • patch_k8s_resourceCan delete

    Patch a Kubernetes resource, like kubectl patch.

  • diagnose_k8s_workloadRead-only

    Collects a correlated incident snapshot for a Kubernetes workload (Deployment, StatefulSet, DaemonSet), verifying referenced ConfigMaps, Secrets, and PVCs, warning events, and automatically…

  • get_k8s_cluster_healthRead-only

    Computes a high-level health scorecard across nodes, workloads, system pods, and control-plane components (GKE cluster state, admission webhooks, and API Priority and Fairness).

  • get_k8s_log_summaryRead-only

    Fetches and deduplicates container logs using pattern fingerprinting to reduce token usage.

  • list_k8s_cluster_issuesRead-only

    Scans a cluster or namespace for abnormal pods (CrashLoopBackOff, OOMKilled, ImagePullBackOff), node pressure, stalled rollouts, quota exhaustion, PDB blocks, admission webhook risks, and API…

Read from the live server on 17 Nov 2026. Read-only, Writes and Can delete are hints the server declares; your client decides whether to ask before running a tool.

Example prompts

  • List all GKE clusters in my project my-project across all locations.

  • Show the logs of the last crashed container for pod web-0 in namespace prod.

  • Check the rollout status of the checkout deployment in the shop namespace.

  • Create a new node pool in cluster demo-cluster in us-central1.

Set up

Every client connects to container.googleapis.com, and Google Cloud asks you to sign in the first time. Pick yours; the page remembers your choice.

Claude Code

  1. Run this in a terminal, in your project folder:
claude mcp add --transport http gke https://container.googleapis.com/mcp
  1. Start Claude Code, type /mcp, pick gke and choose Authenticate. A browser window opens for the Google Cloud sign-in.

Add --scope user to make it available in every project, not just this one.

Claude Desktop

  1. Open Customize → Connectors, click + Add, then Add custom connector.
  2. Name it Google Kubernetes Engine (GKE) and paste this URL:
https://container.googleapis.com/mcp
  1. Click Add, then Connect, and sign in when Google Cloud asks.

Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too.

claude.ai

  1. Open the connector form on claude.ai. This button fills in the name and URL for you:
  1. Check that the URL reads https://container.googleapis.com/mcp and click Add.
  2. Click Connect and sign in when Google Cloud asks.

Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under Organization settings → Connectors.

ChatGPT

  1. On chatgpt.com, go to Plugins, select +, then Add custom MCP server.
  2. Enter a name for the server.
  3. Under Connection, paste https://container.googleapis.com/mcp as the server URL, then for authentication choose OAuth. ChatGPT sends you to Google Cloud to sign in.
  4. Check I understand and want to continue, then select Create as a plugin.

Whether you can add a custom MCP server depends on your ChatGPT plan and your workspace permissions (in Business workspaces, admins and owners can).

Cursor

Or add it by hand to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project):

mcp.json
{
  "mcpServers": {
    "gke": {
      "url": "https://container.googleapis.com/mcp"
    }
  }
}

Cursor shows Needs authentication next to the server. Click the button beside it to sign in.

VS Code

Or from a terminal:

code --add-mcp '{"name":"gke","type":"http","url":"https://container.googleapis.com/mcp"}'

Or commit it to the repo in .vscode/mcp.json:

.vscode/mcp.json
{
  "servers": {
    "gke": {
      "type": "http",
      "url": "https://container.googleapis.com/mcp"
    }
  }
}

VS Code asks you to sign in the first time the server starts.

Devin Desktop

  1. Add it to ~/.config/devin/mcp_config.json (macOS and Linux) or %APPDATA%\devin\mcp_config.json (Windows):
mcp_config.json
{
  "mcpServers": {
    "gke": {
      "serverUrl": "https://container.googleapis.com/mcp"
    }
  }
}
  1. Refresh the MCP server list in Cascade and sign in when asked.

Devin Desktop is the new name for Windsurf. It reads serverUrl (or url) for remote servers.

Codex

codex mcp add gke --url https://container.googleapis.com/mcp
codex mcp login gke

Or edit ~/.codex/config.toml directly:

config.toml
[mcp_servers.gke]
url = "https://container.googleapis.com/mcp"

Gemini CLI

gemini mcp add --transport http gke https://container.googleapis.com/mcp

Then, inside Gemini CLI, run /mcp auth gke to sign in.

This adds it to the current project. Add -s user to use it everywhere.

Any client

Most clients accept this shape. Some name the URL field differently: serverUrl in Devin Desktop, httpUrl in Gemini CLI’s settings file.

{
  "mcpServers": {
    "gke": {
      "type": "http",
      "url": "https://container.googleapis.com/mcp"
    }
  }
}

Zed puts servers under context_servers in its settings. Cline needs "type": "streamableHttp", or it assumes SSE.

Client only starts local servers? Bridge it with npx -y mcp-remote https://container.googleapis.com/mcp.

Embed

Show Google Kubernetes Engine (GKE) in a README or on your site. Each embed links to this page, uses the server’s own URL, and sets no cookies. How embeds work

The card, the iframe and the JSON are in English. Add ?lang=it, fr, de or es to their address for another language.

README badge

Badge preview, lightBadge preview, dark
Markdown
[![Google Kubernetes Engine (GKE) on mcp.tc](https://mcp.tc/i/gke/badge.svg)](https://mcp.tc/i/gke)
HTML
<a href="https://mcp.tc/i/gke"><img src="https://mcp.tc/i/gke/badge.svg" alt="Google Kubernetes Engine (GKE) on mcp.tc" height="20"></a>

It follows the reader’s light or dark mode. Add ?theme=light or ?theme=dark to fix it, or ?style=compact to show the mark without the word.

Website card

HTML
<script src="https://mcp.tc/w/gke.js" async></script>

The card appears where the tag is. Add data-theme="dark" or data-size="compact" to the tag to change it. The file holds everything it needs, so it makes no other requests and sets no cookies.

iframe

HTML
<iframe src="https://mcp.tc/embed/gke" title="Google Kubernetes Engine (GKE) on mcp.tc" width="420" height="200" loading="lazy" allow="clipboard-write" style="border:0;border-radius:8px;max-width:100%"></iframe>

Use it on pages that don’t allow scripts. Add ?theme=light or ?theme=dark to the address to fix the colors.

JSON

The listing as data for your own pages and tools: name, tagline, the server’s own URL, tools and the “Add to” links. Any site can read it (CORS is open).

https://mcp.tc/i/gke.json

What each field means

AI prompt

Paste this into an AI coding assistant, such as Claude Code or Cursor, and it adds the Google Kubernetes Engine (GKE) card to your site.

Markdown
Add the mcp.tc card for Google Kubernetes Engine (GKE), an MCP server, to my website. It is one static script: no build step, no package to install, no cookies.

Put this tag where the card should appear. The card renders right before it:

```html
<script src="https://mcp.tc/w/gke.js" async></script>
```

To show the card somewhere else, put this placeholder there and load the same script once, for example before `</body>`. Keep the link inside: visitors without JavaScript see it.

```html
<div data-mcptc="gke"><a href="https://mcp.tc/i/gke">Google Kubernetes Engine (GKE) on mcp.tc</a></div>
```

Options:
- `data-theme="light"` or `"dark"` on the tag or the placeholder fixes the colors. Without it, the card follows the visitor’s light or dark mode.
- `data-size="compact"` gives a smaller card without the tagline.
- The CSS variable `--mcptc-max-width` on the placeholder or a parent sets the width (default `520px`).
- `?lang=` on the script URL sets the card’s language: `en`, `it`, `fr`, `de` or `es`.

If the site has a Content Security Policy, allow `script-src https://mcp.tc` and `img-src data:` (the icon is inline).

For a README or other Markdown docs, use the badge instead:

```markdown
[![Google Kubernetes Engine (GKE) on mcp.tc](https://mcp.tc/i/gke/badge.svg)](https://mcp.tc/i/gke)
```

Reference: https://mcp.tc/embed

Change history

We read this server’s tool list every 3 hours and record what changes. Last read 18 Nov 2026, 05:33 UTC.

Follow Google Kubernetes Engine (GKE) and we’ll email you when something changes.

  1. , Automatic check

    4 tools added and 1 tool changed.

    Details, 9 Nov 2026, 23:48 UTC

    Added 4

    • diagnose_k8s_workloadRead-only

      Collects a correlated incident snapshot for a Kubernetes workload (Deployment, StatefulSet, DaemonSet), verifying referenced ConfigMaps, Secrets, and PVCs, warning events, and automatically deduplicating container error logs.

    • get_k8s_cluster_healthRead-only

      Computes a high-level health scorecard across nodes, workloads, system pods, and control-plane components (GKE cluster state, admission webhooks, and API Priority and Fairness).

    • get_k8s_log_summaryRead-only

      Fetches and deduplicates container logs using pattern fingerprinting to reduce token usage. Prefer this over get_k8s_logs when triaging crashes or noisy logs.

    • list_k8s_cluster_issuesRead-only

      Scans a cluster or namespace for abnormal pods (CrashLoopBackOff, OOMKilled, ImagePullBackOff), node pressure, stalled rollouts, quota exhaustion, PDB blocks, admission webhook risks, and API Priority and Fairness issues.

    Changed 1

    • create_clusterdescription
      Before

      Creates a new GKE cluster in a given project and location. It's recommended to read the [GKE documentation](https://docs.cloud.google.com/kubernetes-engine/docs/concepts/configuration-overview) to understand cluster configuration options. Cluster creation will default to Autopilot mode, as recommended by GKE best practices. If the user explicitly wants to create a Standard cluster, you need to set autopilot.enabled=false in the cluster configuration. This is similar to running `gcloud container clusters create-auto` or `gcloud container clusters create`.

      After

      Creates a new GKE cluster in a given project and location. It's recommended to read the [GKE documentation](https://docs.cloud.google.com/kubernetes-engine/docs/concepts/configuration-overview) to understand cluster configuration options. For regional locations, cluster creation will default to Autopilot mode, as recommended by GKE best practices. If the user explicitly wants to create a Standard cluster, you need to set autopilot.enabled=false in the cluster configuration. Clusters in zonal locations are always Standard clusters. If a Standard cluster configuration has neither nodePools nor initialNodeCount, the cluster is created without any nodes (older GKE versions reject the request), so include nodePools or initialNodeCount when the user needs nodes to run workloads. This is similar to running `gcloud container clusters create-auto` or `gcloud container clusters create`.

  2. , Automatic check

    1 tool changed.

    Details, 27 Oct 2026, 21:03 UTC

    Changed 1

    • get_k8s_logsinput schema
      • Description of since
        Before

        Optional. Retrieve logs since this duration ago (e.g. "1h", "10m").

        After

        Optional. Retrieve logs since this duration ago (e.g. "1h", "10m"). Only one of this field or sinceTime should be set.

      • Description of sinceTime
        Before

        Optional. Retrieve logs since this time (RFC3339). e.g. "2024-08-30T06:00:00Z".

        After

        Optional. Retrieve logs since this time (RFC3339). e.g. "2024-08-30T06:00:00Z". Only one of this field or since should be set.

  3. , Automatic check

    1 tool changed.

    Details, 16 Oct 2026, 04:32 UTC

    Changed 1

    • get_k8s_resourceinput schema and output schema
      • New parameters: pageSize pageToken
  4. , Automatic check

    Tracking started: 23 tools.

FAQ

Can I paste mcp.tc/i/gke into my MCP client?

No. mcp.tc links are pages, not server addresses. Connect with https://container.googleapis.com/mcp, so your client talks to Google Kubernetes Engine (GKE) directly. The sign-in token only works there anyway. The quick link is for sharing: it opens this page, with setup steps for every client.

Does Google Kubernetes Engine (GKE) need an API key or a sign-in?

Yes, you need a Google Cloud account. The first time your client connects, it opens Google Cloud’s sign-in page. The token goes straight to the server’s own URL, never through mcp.tc.

Is Google Kubernetes Engine (GKE) a remote or a local server?

Remote. Google Cloud hosts it at https://container.googleapis.com/mcp, and it speaks Streamable HTTP. There’s nothing to install.

What can Google Kubernetes Engine (GKE) do?

It has 27 tools, including list_k8s_api_resources, check_k8s_auth and describe_k8s_resource. You can list, get, create and update GKE clusters, create, list, inspect and update node pools and list, inspect and cancel GKE operations.

Which clients can use it?

Any client that supports remote MCP servers: Claude Code, Claude Desktop, claude.ai, ChatGPT, Cursor, VS Code, Devin Desktop, Codex, Gemini CLI, Zed and others. The setup steps cover each one.

Does mcp.tc track changes to Google Kubernetes Engine (GKE)?

Yes. Google Kubernetes Engine (GKE)’s History tab shows each change we find to its tools, down to descriptions and parameters, plus new versions and edits by its owner. Follow the listing to get an email when it changes.

Who wrote this page?

mcp.tc’s robot read Google Kubernetes Engine (GKE)’s own metadata (its MCP handshake, tool list and public pages), and an AI model drafted the text from it. A person reviews anything the checks can’t confirm. The text can still be wrong, so if you spot a mistake, use Report this listing on this page.

mcp.tc isn’t affiliated with Google Cloud. This page was built from Google Kubernetes Engine (GKE)’s public metadata, last checked on 17 Nov 2026, and an AI model wrote the description, so it can be wrong. Names and marks belong to their owners. Something off? Report this listing.